The Pragmatics of Indirect Commands in Collaborative Discourse
This work addresses the challenge of making human-AI interactions more natural by handling non-imperative commands, though it is incremental as it focuses on a specific utterance family in a limited domain.
The paper tackled the problem of enabling artificial assistants to understand indirect commands like locatives (e.g., 'The chair is in the other room') in collaborative games, and demonstrated that models with domain-specific grounding can effectively perform the pragmatic reasoning needed for more robust natural language interaction.
Today's artificial assistants are typically prompted to perform tasks through direct, imperative commands such as \emph{Set a timer} or \emph{Pick up the box}. However, to progress toward more natural exchanges between humans and these assistants, it is important to understand the way non-imperative utterances can indirectly elicit action of an addressee. In this paper, we investigate command types in the setting of a grounded, collaborative game. We focus on a less understood family of utterances for eliciting agent action, locatives like \emph{The chair is in the other room}, and demonstrate how these utterances indirectly command in specific game state contexts. Our work shows that models with domain-specific grounding can effectively realize the pragmatic reasoning that is necessary for more robust natural language interaction.